标题:Long-time Object Tracking Based on Hierarchical Convolution Features
作者:Sheng, Xiaoxiao ;Liu, Yungang
作者机构:[Sheng, X] School of Control Science and Engineering, Shandong University, Jinan, 250061, China;[ Liu, Y] School of Control Science and Engineering, S 更多
会议名称:2018 Chinese Automation Congress, CAC 2018
会议日期:30 November 2018 through 2 December 2018
来源:Proceedings 2018 Chinese Automation Congress, CAC 2018
出版年:2019
页码:1510-1515
DOI:10.1109/CAC.2018.8623058
摘要:Traditional object tracking methods, mainly based on manual features (e.g., histograms of oriented gradients, color names and color histograms), have limited ability to complex scenarios. As convolution neural network has achieved great progress on image classification, it has been proved to have strong feature extraction ability and superiority to traditional object tracking methods. In this paper, we propose an improved object tracking method, where the pre-trained convolution neural network is used for hierarchical feature extraction. Moreover, a robust model updating strategy and an object re-detection strategy are introduced to our method. Several experiments on public data sets are provided to demonstrate that our method indeed improves the performance in illumination changing, occlusion, low resolution, while enhancing the overall accuracy and success rates. © 2018 IEEE.
收录类别:EI;SCOPUS
资源类型:会议论文;期刊论文
原文链接:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85062785241&doi=10.1109%2fCAC.2018.8623058&partnerID=40&md5=a4900c6c917e169a7d6d85babf3a6ee3
TOP